Alibaba's multimodal generation model from the Wan AI suite, supporting text-to-video, image-to-video, reference-to-video with audio, and text-to-image, in both Chinese and English

How Wan 2.6 performs

Rankings based on human votes in the Lumenfall Arena, where real users pick their favorite without knowing which model made which image.

All categories

Wan 2.6 competes across 7 categories in the arena

Aesthetics

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Human Fidelity

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Physics & Realism

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Scenes & Atmospherics

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Camera Control

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Motion Quality

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival

Preservation

Image-to-Video
Ranked #2 of 3 models · 15.8% win rate Leaderboard
#2
of 3 models · 15.8% wins
#1 is Seedance 2.0
Ranked using Celebrity Arrival